计算机科学
过程(计算)
反向传播
人工神经网络
中央处理器
培训(气象学)
投影(关系代数)
并行计算
人工智能
计算机工程
计算机硬件
算法
操作系统
物理
气象学
作者
Tao Fang,Jingwei Li,Tongyu Wu,Ming Cheng,Xiaowen Dong
摘要
As a new emerging machine learning mechanism, optical diffractive deep neural network (OD2NN) has been intensively studied recently due to its incomparable advantages on speed and power efficiency. However, the training process of the OD2NN with traditional back-propagation (BP) method is always time-consuming. Here, we introduce the biologically plausible training methods without feedback to accelerate the training process of the hybrid OD2NN. Direct feedback alignment (DFA), error-sign-based DFA (sDFA) and direct random target projection (DRTP) are utilized and evaluated in the training process of the hybrid OD2NN respectively. For the hybrid OD2NN with 20 diffractive layers, about 160× (DFA; CPU), 30× (DFA; GPU), 170× (sDFA; CPU), 32× (sDFA; GPU), 158× (DRTP; CPU) and 32× (DRTP; GPU) accelerations are achieved respectively without significant loss of accuracy, compared with the training process using BP method on CPU or GPU.
科研通智能强力驱动
Strongly Powered by AbleSci AI